© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81530
    Prev
    Next
    INDEX
    Explanations

    musical toy

    np_acts-logits-general · gemini-2.5-flash-lite

    automating customer responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     моди
    0.54
    Emerald
    0.50
    IRM
    0.49
    ز
    0.48
     микро
    0.47
     druhé
    0.47
    を備
    0.47
    が行
    0.47
     ribu
    0.46
     Bulb
    0.46
    POSITIVE LOGITS
    tingham
    0.43
     to
    0.43
    enian
    0.43
    诀
    0.42
    reau
    0.41
    ican
    0.41
    leges
    0.41
    ént
    0.41
     get
    0.41
    训
    0.40
    Activations Density 0.000%

    No Known Activations